Band-sensitive seizure onset detection via CSP-enhanced EEG features

Research output: Contribution to journalArticle

18 Citations (Scopus)

Abstract

This paper presents two novel epileptic seizure onset detectors. The detectors rely on a common spatial pattern (CSP)-based feature enhancement stage that increases the variance between seizure and nonseizure scalp electroencephalography (EEG). The proposed feature enhancement stage enables better discrimination between seizure and nonseizure features. The first detector adopts a conventional classification stage using a support vector machine (SVM) that feeds the energy features extracted from different subbands to an SVM for seizure onset detection. The second detector uses logical operators to pool SVM seizure onset detections made independently across different EEG spectral bands. The proposed detectors exhibit an improved performance, with respect to sensitivity and detection latency, compared with the state-of-the-art detectors. Experimental results have demonstrated that the first detector achieves a sensitivity of 95.2%, detection latency of 6.43. s, and false alarm rate of 0.59. per. hour. The second detector achieves a sensitivity of 100%, detection latency of 7.28. s, and false alarm rate of 1.2. per hour for the MAJORITY fusion method.

Original languageEnglish
Pages (from-to)77-87
Number of pages11
JournalEpilepsy and Behavior
Volume50
DOIs
Publication statusPublished - 1 Sep 2015

Fingerprint

Electroencephalography
Seizures
Scalp
Epilepsy
Support Vector Machine

Keywords

  • Common spatial pattern
  • EEG
  • Epilepsy
  • Seizure onset detection

ASJC Scopus subject areas

  • Neurology
  • Clinical Neurology
  • Behavioral Neuroscience

Cite this

@article{3a1a8a6e5fbd4d94b51643fc86e7cb10,
title = "Band-sensitive seizure onset detection via CSP-enhanced EEG features",
abstract = "This paper presents two novel epileptic seizure onset detectors. The detectors rely on a common spatial pattern (CSP)-based feature enhancement stage that increases the variance between seizure and nonseizure scalp electroencephalography (EEG). The proposed feature enhancement stage enables better discrimination between seizure and nonseizure features. The first detector adopts a conventional classification stage using a support vector machine (SVM) that feeds the energy features extracted from different subbands to an SVM for seizure onset detection. The second detector uses logical operators to pool SVM seizure onset detections made independently across different EEG spectral bands. The proposed detectors exhibit an improved performance, with respect to sensitivity and detection latency, compared with the state-of-the-art detectors. Experimental results have demonstrated that the first detector achieves a sensitivity of 95.2{\%}, detection latency of 6.43. s, and false alarm rate of 0.59. per. hour. The second detector achieves a sensitivity of 100{\%}, detection latency of 7.28. s, and false alarm rate of 1.2. per hour for the MAJORITY fusion method.",
keywords = "Common spatial pattern, EEG, Epilepsy, Seizure onset detection",
author = "Marwa Qaraqe and Muhammad, {Muhammad Ismail} and Erchin Serpedin",
year = "2015",
month = "9",
day = "1",
doi = "10.1016/j.yebeh.2015.06.002",
language = "English",
volume = "50",
pages = "77--87",
journal = "Epilepsy and Behavior",
issn = "1525-5050",
publisher = "Academic Press Inc.",

}

TY - JOUR

T1 - Band-sensitive seizure onset detection via CSP-enhanced EEG features

AU - Qaraqe, Marwa

AU - Muhammad, Muhammad Ismail

AU - Serpedin, Erchin

PY - 2015/9/1

Y1 - 2015/9/1

N2 - This paper presents two novel epileptic seizure onset detectors. The detectors rely on a common spatial pattern (CSP)-based feature enhancement stage that increases the variance between seizure and nonseizure scalp electroencephalography (EEG). The proposed feature enhancement stage enables better discrimination between seizure and nonseizure features. The first detector adopts a conventional classification stage using a support vector machine (SVM) that feeds the energy features extracted from different subbands to an SVM for seizure onset detection. The second detector uses logical operators to pool SVM seizure onset detections made independently across different EEG spectral bands. The proposed detectors exhibit an improved performance, with respect to sensitivity and detection latency, compared with the state-of-the-art detectors. Experimental results have demonstrated that the first detector achieves a sensitivity of 95.2%, detection latency of 6.43. s, and false alarm rate of 0.59. per. hour. The second detector achieves a sensitivity of 100%, detection latency of 7.28. s, and false alarm rate of 1.2. per hour for the MAJORITY fusion method.

AB - This paper presents two novel epileptic seizure onset detectors. The detectors rely on a common spatial pattern (CSP)-based feature enhancement stage that increases the variance between seizure and nonseizure scalp electroencephalography (EEG). The proposed feature enhancement stage enables better discrimination between seizure and nonseizure features. The first detector adopts a conventional classification stage using a support vector machine (SVM) that feeds the energy features extracted from different subbands to an SVM for seizure onset detection. The second detector uses logical operators to pool SVM seizure onset detections made independently across different EEG spectral bands. The proposed detectors exhibit an improved performance, with respect to sensitivity and detection latency, compared with the state-of-the-art detectors. Experimental results have demonstrated that the first detector achieves a sensitivity of 95.2%, detection latency of 6.43. s, and false alarm rate of 0.59. per. hour. The second detector achieves a sensitivity of 100%, detection latency of 7.28. s, and false alarm rate of 1.2. per hour for the MAJORITY fusion method.

KW - Common spatial pattern

KW - EEG

KW - Epilepsy

KW - Seizure onset detection

UR - http://www.scopus.com/inward/record.url?scp=84934293104&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84934293104&partnerID=8YFLogxK

U2 - 10.1016/j.yebeh.2015.06.002

DO - 10.1016/j.yebeh.2015.06.002

M3 - Article

VL - 50

SP - 77

EP - 87

JO - Epilepsy and Behavior

JF - Epilepsy and Behavior

SN - 1525-5050

ER -